Abstract
Data owners are increasingly liable for the potential harm caused by using their data on underprivileged communities. Stakeholders seek to identify data characteristics that lead to biased algorithms against specific demographic groups, such as race, gender, age, or religion. We focus on identifying feature subsets of datasets where the ground truth response function from features to observed outcomes differs across demographic groups. To achieve this, we propose FORESEE, a decision tree-based algorithm that generates a score indicating the likelihood of an individual’s response varying with sensitive attributes. Our approach enables us to identify individuals most likely to be misclassified by various classifiers, including Random Forest, Logistic Regression, Support Vector Machine, Multi-Layer Perceptron, and k-Nearest Neighbors. The advantage of our approach is that it allows stakeholders to identify risky samples that may contribute to discrimination and use FORESEE to estimate the risk of upcoming samples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adkins, D., et al.: Method cards for prescriptive machine-learning transparency. In: 2022 IEEE/ACM 1st International Conference on AI Engineering-Software Engineering for AI (CAIN), pp. 90–100. IEEE (2022)
Adkins, D., et al.: Prescriptive and descriptive approaches to machine-learning transparency. In: CHI Conference on Human Factors in Computing Systems Extended Abstracts, pp. 1–9 (2022)
Asuncion, A., Newman, D.: UCI machine learning repository (2007)
Bao, M., et al.: It’s compaslicated: the messy relationship between rai datasets and algorithmic fairness benchmarks. arXiv preprint arXiv:2106.05498 (2021)
Bellamy, R.K.E., et al.: AI Fairness 360: an extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias (2018)
Bird, S., et al.: Fairlearn: a toolkit for assessing and improving fairness in AI. Technical Report. MSR-TR-2020-32, Microsoft (2020)
Buolamwini, J., Gebru, T.: Gender shades: intersectional accuracy disparities in commercial gender classification. In: Conference on Fairness, Accountability and Transparency, pp. 77–91. PMLR (2018)
Chen, I., Johansson, F.D., Sontag, D.: Why is my classifier discriminatory? Adv. Neural Inf. Process. Syst. 31, 1–12 (2018)
Chipman, H.A., George, E.I., McCulloch, R.E.: Bart: bayesian additive regression trees. Ann. Appl. Stat. 4(1), 266–298 (2010)
Ensign, D., Friedler, S.A., Neville, S., Scheidegger, C., Venkatasubramanian, S.: Runaway feedback loops in predictive policing. In: Conference on Fairness, Accountability and Transparency, pp. 160–171. PMLR (2018)
Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., Venkatasubramanian, S.: Certifying and removing disparate impact. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 259–268 (2015)
Fu, R., Huang, Y., Singh, P.V.: Crowds, lending, machine, and bias. Inf. Syst. Res. 32(1), 72–92 (2021)
Gebru, T., et al.: Datasheets for datasets. Commun. ACM 64(12), 86–92 (2021)
Gitiaux, X., Rangwala, H.: Multi-differential fairness auditor for black box classifiers. arXiv preprint arXiv:1903.07609 (2019)
Gitiaux, X., Rangwala, H.: Fair representations by compression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11506–11515 (2021)
Hill, J.L.: Bayesian nonparametric modeling for causal inference. J. Comput. Graph. Stat. 20(1), 217–240 (2011)
Ilvento, C.: Metric learning for individual fairness. arXiv preprint arXiv:1906.00250 (2019)
Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1–33 (2012)
Kearns, M., Neel, S., Roth, A., Wu, Z.S.: Preventing fairness gerrymandering: auditing and learning for subgroup fairness. In: International Conference on Machine Learning, pp. 2564–2572. PMLR (2018)
Kizilcec, R.F., Lee, H.: Algorithmic fairness in education. arXiv preprint arXiv:2007.05443 (2020)
Lee, M.S.A., Singh, J.: Risk identification questionnaire for detecting unintended bias in the machine learning development lifecycle. In: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp. 704–714 (2021)
Mitchell, M., et al.: Model cards for model reporting. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, pp. 220–229 (2019)
Pessach, D., Shmueli, E.: Algorithmic fairness. arXiv preprint arXiv:2001.09784 (2020)
ProPublica: How we analyzed the compas recidivism algorithm. ProPublica (2016)
Vetrò, A., Torchiano, M., Mecati, M.: A data quality approach to the identification of discrimination risk in automated decision making systems. Gov. Inf. Q. 38(4), 101619 (2021)
Wen, M., Bastani, O., Topcu, U.: Fairness with dynamics. arXiv preprint arXiv:1901.08568 (2019)
Acknowledgements
This study was supported by the National Agency for Research and Development (ANID - Agencia Nacional de Investigación y Desarrollo/Subdirección de Capital Humano), “Becas Chile” Doctoral Fellowship 2020 program; Grant No. 72210492 to Jonathan Patricio Vasquez Verdugo.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vasquez, J., Gitiaux, X., Rangwala, H. (2023). Estimating the Risk of Individual Discrimination of Classifiers. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13935. Springer, Cham. https://doi.org/10.1007/978-3-031-33374-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-33374-3_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33373-6
Online ISBN: 978-3-031-33374-3
eBook Packages: Computer ScienceComputer Science (R0)